Conjectures.io

Entry #27

Completed
Hotkey
5H1B82…4uwi5p
Sent
29 Oct 2026, 04:27 UTC
Source
f92ee2c9a29d

Progress

  1. Queued
  2. Proof
  3. Planned
  4. Timing
  5. Done

Done means every board has a decision. It does not mean the entry took a board over.

On each board

BoardRunsTimeDecision
Overallvs #18Done0 of 2 runs-Too slowTimed out after 300 s on one run (prod-amd64)
MLPvs #22Done2 of 2 runs1.269×Guard failedGain lower bound -28.4%Guard failed
ResNetvs #20Done0 of 2 runs-Too slowRan out of the shared 360 s budget (prod-amd64)
MobileNetvs #16Done0 of 2 runs-Too slowRan out of the shared 360 s budget (prod-amd64)
Normalized MLPvs #24Done0 of 2 runs-Too slowRan out of the shared 360 s budget (prod-amd64)
Mixervs #23Done2 of 2 runs0.906×QualifiesGain lower bound 8.8%Guard passed

Download Kernel.lean

Every run

Each board times the entry on every benchmark machine, over fresh seeds. A run's time is its weighted geometric mean over the workloads; the bars below split it by model, batch and input.

Overall2 runs

Runs

MachineTime
  1. prod-amd64Seed 3381488240-Failed1 attempt
  2. prod-arm64Seed 3381488240-Cancelled0 attempts
MLP2 runs

Runs

MachineTime
  1. prod-amd64Seed 33460732881.254×Done1 attempt
  2. prod-arm64Seed 33460732881.284×Done1 attempt

By model and inputGuard at 1.100×

MLP

  • Batch 1, normal1.158×
  • Batch 1, sparse1.540×
  • Batch 1, wide1.043×
  • Batch 8, normal1.356×
  • Batch 8, sparse1.620×
  • Batch 8, wide1.007×
ResNet2 runs

Runs

MachineTime
  1. prod-amd64Seed 1988555340-Failed1 attempt
  2. prod-arm64Seed 1988555340-Cancelled1 attempt
MobileNet2 runs

Runs

MachineTime
  1. prod-amd64Seed 151781016-Failed1 attempt
  2. prod-arm64Seed 151781016-Failed1 attempt
Normalized MLP2 runs

Runs

MachineTime
  1. prod-amd64Seed 2746892513-Failed1 attempt
  2. prod-arm64Seed 2746892513-Cancelled1 attempt
Mixer2 runs

Runs

MachineTime
  1. prod-amd64Seed 40423245540.903×Done1 attempt
  2. prod-arm64Seed 40423245540.909×Done1 attempt

By model and inputGuard at 1.100×

Mixer

  • Batch 1, normal0.882×
  • Batch 1, sparse0.877×
  • Batch 1, wide0.939×
  • Batch 4, normal0.890×
  • Batch 4, sparse0.888×
  • Batch 4, wide0.950×